Information processing device, information processing method, and information processing program

Abstract

Provided are an information processing device and others, the information processing device comprising: an input value reception unit that receives an input value for each item; a prompt setting unit that sets, for each item, a prompt for correcting the input value received in relation to the item; and a correction value generation unit that inputs the received input value and a prompt set for the item to a trained AI model so as to generate a correction value for the received input value.

Description

Information Processing Apparatus, Information Processing Method, and Information Processing Program

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program for assisting input of characters, numerical values, and the like.

[0002] When applying for products, services, events, questionnaires, etc., users input various necessary items into an application form. For example, for an input item for "company name", the phrase "Limited Company" is expected as the input value, and for an input item for "landline phone number", a 10-digit numerical sequence is expected as the input value. However, there are quite a few cases where inputs different from the expected input values are made depending on the item.

[0003] As a technology to address such a situation, for example, by preliminarily preparing a thesaurus like the technology disclosed in Japanese Unexamined Patent Application Publication No. 2021-189694, for an input of an abbreviation such as "(Co., Ltd.)", the official name obtained by referring to the thesaurus is accepted as the input word.

[0004] However, when a 9-digit numerical sequence is input into the above-mentioned input item for a landline phone number, it cannot be handled by the thesaurus, and it is impossible to handle various types of inputs such as "email address" and "location" with a dictionary function.

[0005] Also, in an item for inputting a date such as "date of birth", for example, it is conceivable to perform input support by preliminarily providing a processing function for converting a date input in the era name to a date in the Gregorian calendar, but there is also a problem that such function provision is not easy to develop. In view of such circumstances, an input support technology with better usability is required.

[0006] Therefore, in order to solve the above problems, the present invention provides the following information processing device, etc. Specifically, it provides an information processing device having an input value receiving unit that receives input values ​​for each item, a prompt setting unit that sets a prompt for correcting the input value received for each item, and a correction value generation unit that inputs the received input value and the prompt set for that item to a trained AI model and generates a corrected value of the received input value.

[0007] Furthermore, in addition to the above features, the present invention provides an information processing device in which the input value is an electronic object other than a symbol.

[0008] Furthermore, in addition to the above features, the present invention provides an information processing device that further includes a correction value setting unit that sets the generated correction value as the input value for that item, replacing the input value from which the correction value was generated.

[0009] In addition to the features described above, the input value receiving unit provides an information processing device that receives input values ​​based on selections made on a viewer.

[0010] In addition to the features described above, the input value receiving unit acquires information contained in or associated with the data to be received as input values, as peripheral information, and the correction value generation unit inputs the acquired peripheral information regarding the received input values ​​into the trained AI model to generate a correction value for the received input values.

[0011] Furthermore, the present invention provides an information processing method executed by an information processing device, comprising: an input value reception step of receiving input values ​​for each item; a prompt setting step of setting a prompt for each item to correct the input values ​​received for that item; and a correction value generation step of inputting the received input values ​​and the prompts set for that item into a trained AI model to generate a corrected value of the received input values.

[0012] Furthermore, the present invention provides an information processing program that causes an information processing device to execute the following steps: an input value reception step that receives input values ​​for each item; a prompt setting step that sets a prompt for each item to correct the input values ​​received for that item; and a correction value generation step that inputs the received input values ​​and the prompts set for that item into a trained AI model to generate a corrected value for the received input values.

[0013] The present invention provides an information processing device that offers superior input assistance compared to the prior art.

[0014] A block diagram showing an example of the functional configuration of the information processing device in the embodiment. A conceptual diagram illustrating a database using the embodiment. A conceptual diagram showing an example of how input values ​​are received on a viewer. A conceptual diagram showing an example of the hardware configuration for realizing the information processing device in the embodiment. A flowchart showing a simplified example of the processing flow of the information processing device in the embodiment.

[0015] Embodiments of the present invention will be described below with reference to the accompanying drawings. However, the present invention is not limited in any way to these embodiments, and can be implemented in various ways without departing from its essence.

[0016] <Examples> <Summary> In this invention, a prompt (hereinafter sometimes referred to as a correction prompt) is set for each item that accepts input such as characters, to correct the received input value. The corrected value obtained by the prompt is then used in place of the input value and becomes the set value for that item. This allows for input that conforms to the intent of each item.

[0017] The following describes the functions and processing flow of the information processing device, as well as the hardware components. The functional blocks of this system described below can be implemented as a combination of hardware and software. Specifically, if a computer is used, these may include hardware components such as a CPU (Central Processing Unit), main memory, a bus, or secondary storage devices (hard disk drives, non-volatile memory, storage media such as CDs and DVDs, and their readers), input devices used for information input, printing equipment, display devices, and other external peripheral devices, as well as interfaces for these external peripheral devices, communication interfaces, driver programs and other application programs for controlling the hardware, and user interface applications. The CPU's arithmetic processing, based on programs deployed in main memory, processes and stores data input from input devices and other interfaces, and stored in memory and on the hard disk, and generates instructions for controlling the aforementioned hardware and software. Alternatively, the functional blocks of this system may be implemented using dedicated hardware.

[0018] Furthermore, this invention can be realized not only as a system but also as a method. Moreover, a part of such an invention can be configured as software. In addition, programs used to cause a computer to execute such software, and recording media on which such programs are fixed, are naturally included within the technical scope of this invention (as is the case throughout this specification).

[0019] <Functional Configuration> Figure 1 is a block diagram showing an example of the functional configuration of the information processing device of the embodiment. As shown in Figure 1, the information processing device 100 has an input value receiving unit 101, a prompt setting unit 102, a correction value generation unit 103, and a correction value setting unit 194.

[0020] In this embodiment, the trained AI model is a machine learning model that has been pre-trained and is capable of handling general-purpose tasks. A well-known example is the Language Language Model (LLM), but it may also be a different model, such as a small-scale language model or a multimodal language model that can handle images and other formats.

[0021] <Input Value Reception Unit> The input value reception unit 101 has the function of receiving input values ​​for each item. An item is each individual item that indicates the content of something. For example, in an application form for applying for a health checkup, there may be various items such as "name," "date of birth," "gender," "medical history," and "medications currently being taken." If the items are for searching, they may include items such as "target image," "target name," and "similar range." Database columns and variables in programs are also items.

[0022] The input values ​​for each item are the content of the items listed above. For example, in the application form above, the input values ​​for each item would be "Ichiro Tanaka", "March 4, 1990", "Male", "Appendicitis", and "Anti-allergy medication".

[0023] Furthermore, the various field names such as "Humanities" and "Nutrition" entered in the "Field" field during a literature search will be used as input values. In the case of a document management system, the input values ​​will be "d5g109" entered in the "Document Number" field and the uploaded image in the "Signature Image" field.

[0024] Thus, input values ​​include not only symbols (letters, numbers), but also various electronic objects that can be created, processed, and stored in a digital environment, such as images, diagrams, graphs, BIM (Building Information Modeling), 2D CAD (Computer Aided Design), 3D CAD, 3D models, and audio.

[0025] Input values ​​can be accepted in various ways. For example, users can input text, upload images, specify strings written in a Word file, or specify cells in an Excel file. Furthermore, as will be described later, it is also possible to configure the system to accept input values ​​by selection on a viewer.

[0026] Furthermore, there are modes in which pre-registered input values ​​are accepted based on some trigger, and modes in which values ​​extracted from a pre-registered file are accepted based on some trigger. More specifically, one mode is to use a user click as a trigger to extract the "building name" from a pre-registered drawing and use that as the input value. In addition to modes in which the user inputs on the UI (User Interface) screen, there are also modes in which variables passed via API (Application Programming Interface) or other scripts are accepted as input values.

[0027] Figure 2 is a conceptual diagram illustrating a database using this embodiment. In the illustrated "High-rise Building Database" 201, the search items 202 include "Name," "Nearest Station," "Height," and "Completion Date," and accept text and numerical input values. When the search button 204 is pressed, a search process is performed based on the accepted search conditions, and the search results 205 are displayed. In addition, in the "Image" item 203, an image can be uploaded as input value, and a process is performed to search for buildings that correspond to the buildings included (pictured) in that image. Furthermore, input text and images may be used in a single search process.

[0028] <Prompt Setting Unit> The prompt setting unit 102 has the function of setting a prompt for each of the items to correct the input value received in the item. Prompt setting can be done in various ways, such as receiving prompts created by the user, receiving and storing prompt settings in advance, and then receiving modifications to the stored prompts.

[0029] Furthermore, you can set prompts to be input to the trained AI model in conjunction with the accumulated prompts, or you can combine multiple accumulated prompts to set a single prompt. For example, if you have accumulated a prompt that corrects the input number to lowercase and a prompt that infers a 10-digit number and uses it as the correction value if a number other than a 10-digit number is entered, you can combine these two prompts to create a single prompt.

[0030] Input value correction involves correcting errors or deficiencies in input values, or revising their expression to a suitable format. For example, this could involve changing abbreviations to full names, or changing dates entered in the Japanese era system to the Western calendar when they should be entered in the Western calendar. Input value correction also includes correcting the structure and composition of the data to be entered, converting the size of entered data to an appropriate size, and deleting inappropriate objects if they are included in the input objects.

[0031] For example, in the "High-Rise Building Database" shown in Figure 2, the prompt for correction in the "Nearest Station" input field is set as follows: "The data to be entered in this data field is for railway stations within Japan. If a station name that does not exist is entered, please infer and correct it with a real station with a similar name." Similarly, the prompt for correction in the "Completion Date" input field is set as follows: "This data field is for the Gregorian calendar. If a date using the Japanese era name such as Heisei is entered, please convert it to the Gregorian calendar."

[0032] Furthermore, the input field for "Image" 203 includes a prompt for correction, stating, "This data field will contain a 500x500px image. If the image is not that size, please correct it to that size and save it."

[0033] In addition to the example in Figure 2, there can be various other prompts for correction. For example, a prompt could be set for the "Floor Plan" item, such as, "This data item will contain the rectangle of the room. Only horizontal and vertical line segments connected at a 90-degree angle will be saved. If there are any other curves or diagonal lines, please correct them and save." Also, in the input of a piping design system, a prompt could be set, such as, "This data item will contain the 3D model of the piping. If there are any other objects, please delete them and save only the piping."

[0034] <Correction Value Generation Unit> The correction value generation unit 103 has the function of inputting the received input value and the prompt set for that item into a trained AI model and generating a correction value for the received input value. The following is an example of an input value and the corrected correction value. When the input value of the item "Nearest Station" is "Omotesando", the correction value "Omotesando" is generated. When the input value of the item "Completion Date" is "October 2008", the correction value "October 2008" is generated.

[0035] Furthermore, if the input value is an object such as an image, which was used as an example prompt for correction, the generated correction will be an image resized to a specified size, or an image with unsuitable objects removed or corrected. Note that if the input value is appropriate for that item, the generated correction value may be the same as the input value.

[0036] The generated correction values ​​may or may not be displayed. It may also be indicated whether or not the input values ​​have been corrected. Furthermore, if multiple correction values ​​are generated, all generated correction values ​​may be displayed, along with a prompt to choose which one to use as the correction value.

[0037] <Correction Value Setting Unit> The correction value setting unit 104 has the function of setting the generated correction value as the input value for that item, replacing the input value from which it was generated. The correction value may be set by immediately setting the generated correction value as an input value as an internal process without user involvement, or by displaying the generated correction value and then accepting user selection or confirmation operations. The set correction value may then be processed as a search condition entered in a search process, or as input data for database construction.

[0038] <Selection of input values ​​on the viewer> The input value receiving unit can be configured to accept input values ​​by selection on the viewer. Figure 3 is a conceptual diagram showing an example of how input values ​​are accepted on the viewer.

[0039] As shown in Figure 3, the bridge database 301 displayed on the screen has the "Rainbow Bridge Basic Data" file 302, which is the target of data input, opened and displayed in the viewer. This file contains various bridge data such as "Bridge Name" and "Road Surface Type". On the left side of the screen, the input field 303 for data input from the target file is displayed.

[0040] For example, when trying to input the bridge type classification of the target file, Rainbow Bridge, into the "Bridge Type Classification" input field 304, the finger cursor 305 is moved to the area where the bridge type classification "Road Bridge" is displayed. This encloses the word "Road Bridge" in a rectangular frame 306. By clicking or performing other operations in this state, the "Road Bridge" enclosed in the rectangular frame is accepted as the input value for the "Bridge Type Classification" item in the input field.

[0041] Also, for example, if a correction prompt such as "Please correct the input of this major diameter length to a numerical value in km" is set in the input field for "major diameter length", when the user clicks on the number "520", it is corrected to a numerical value of 0.52 by this correction prompt and set in the input field. At this time, in order to determine whether the selected "520" in the viewer is in km or m units, the peripheral information of the selected number "520" (in this case, the unit "(m)" described on the left side of "520") is also input into the learned AI model, and the correction is executed.

[0042] In this way, the input value reception unit can be configured to acquire, as peripheral information, information included in or associated with the data for which the input value is to be received, and information regarding the information selected as the input value (such as information on input conditions and description guidelines). Then, in the correction value generation unit, the acquired peripheral information regarding the received input value can be input into the learned AI model to generate a correction value for the received input value.

[0043] In this way, by further moving the finger cursor to the display area of the "suspension bridge" which is the "bridge type", the suspension bridge becomes a surrounded display by a square frame, and can be further accepted as the input value of the "bridge type" item in the input field by clicking or the like.

[0044] The selection of the target on the viewer can be performed in various ways. For example, when selecting an input value from an image file, a specific range can be selected on the viewer that opens the image file, and the range can be selected as the input value. Also, when selecting a specific layer on the viewer that opens a CAD file, the layer can be selected as the input value.

[0045] Furthermore, it is possible to select content that does not explicitly exist within the data. For example, by opening a BIM file in a viewer and selecting the space between specific objects within that viewer, the distance between those objects can be selected as the input value. Similarly, by opening a spreadsheet such as Excel in a viewer and selecting a specific cell, that cell can be selected as the input value.

[0046] Furthermore, it is possible to configure the system so that clicking or performing other operations on an input value already entered in an input field displays the area on the viewer where that input value is selected. For example, in the example in Figure 3, if "Road Bridge" is accepted as the input value for the bridge type classification in the input field, moving the finger cursor to the display area of ​​this input field and performing operations such as clicking there will highlight the "Road Bridge" display area on the viewer where the entered road bridge is selected by surrounding it with a frame or making it blink. By configuring the system in this way, the correspondence between the input value and the location in the file where that input value is selected becomes clear, making it easier to perform operations such as changing the selection of the input value.

[0047] <Hardware Configuration> Figure 4 is a conceptual diagram showing an example of the hardware configuration for realizing the information processing device of the embodiment. As shown in the figure, the information processing device 400 has a CPU 401 that performs various calculations, a RAM 402 which is a volatile recording medium, a storage device 403 such as a flash memory or HDD which is a non-volatile storage medium, a communication interface 404, and an input / output interface 405. The RAM 402 reads programs that perform various calculations for the CPU 401 to execute and provides a work area (work area) for those programs. In addition, multiple addresses are assigned to the RAM 402, and programs executed by the CPU 401 can exchange data with each other and perform processing by identifying and accessing these addresses.

[0048] Here, each function of the input value reception unit 101, prompt setting unit 102, correction value generation unit 103, and correction value setting unit 104 of the information processing apparatus 100 in FIG. 1 is mainly realized by the CPU 401, RAM 402, and input / output interface 405 in FIG. 4. Also, when using a pre-trained AI model existing externally, each function is realized by mutually exchanging signals and information via the communication interface 404 and the input / output interface 405.

[0049] <Processing flow> FIG. 5 is a flowchart briefly showing an example of the processing flow of the information processing apparatus of the embodiment. First, an input value is received for each item (S501: input value reception step). Then, a prompt for correcting the input value received in the item is set for each item (S502: prompt setting step). Then, the received input value and the set prompt for that item are input to a pre-trained AI model to generate a correction value for the received input value (S503: correction value generation step). Then, the generated correction value is set as the input value for that item in place of the input value that was the source of the generation (S504: correction value setting step).

[0050] <Effect> According to the information processing apparatus of the present embodiment, it is possible to provide an information processing apparatus that performs excellent input support compared to the prior art.

[0051] 100, 400: Information processing apparatus 101: Input value reception unit 102: Prompt setting unit 103: Correction value generation unit 104: Correction value setting unit 401: CPU 402: RAM 403: Storage 404: Communication interface 405: Input / output interface

Claims

1. An information processing device comprising: an input value receiving unit that receives input values ​​for each item; a prompt setting unit that sets a prompt for each item to correct the input value received for that item; and a correction value generation unit that inputs the received input value and the prompt set for that item to a trained AI model to generate a corrected value for the received input value.

2. The information processing apparatus according to claim 1, wherein the input value is an electronic object other than a symbol.

3. The information processing apparatus according to claim 1, further comprising a correction value setting unit that sets the generated correction value as the input value for the item in place of the input value from which it was generated.

4. The information processing apparatus according to claim 1 or 2, wherein the input value receiving unit receives input values ​​by selection on a viewer.

5. The information processing apparatus according to claim 4, wherein the input value receiving unit acquires information contained in or associated with the data to be received as input values, and information related to the information to be selected as an input value, as peripheral information, and the correction value generation unit inputs the acquired peripheral information regarding the received input value to the trained AI model to generate a correction value for the received input value.

6. An information processing method executed by an information processing device, comprising: an input value reception step of receiving input values ​​for each item; a prompt setting step of setting a prompt for each item to correct the input values ​​received for the item; and a correction value generation step of inputting the received input values ​​and the prompts set for that item into a trained AI model to generate a corrected value of the received input values.

7. An information processing program that causes an information processing device to execute: an input value reception step that receives input values ​​for each item; a prompt setting step that sets a prompt for each item to correct the input values ​​received for the item; and a correction value generation step that inputs the received input values ​​and the prompts set for that item into a trained AI model to generate a corrected value for the received input values.

Images